File size: 10,826 Bytes
3672502
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
"""
Conversation prompt templates.
"""

import dataclasses
from enum import Enum, auto
from typing import Any, List


class SeparatorStyle(Enum):
    """Different separator style."""

    ADD_COLON_SINGLE = auto()
    ADD_COLON_TWO = auto()
    NO_COLON_SINGLE = auto()
    BAIZE = auto()
    DOLLY = auto()
    RWKV = auto()


@dataclasses.dataclass
class Conversation:
    """A class that keeps all conversation history."""

    # System prompts
    system: str
    # Two roles
    roles: List[str]
    # All messages
    messages: List[List[str]]
    # Offset of few shot examples
    offset: int
    # Separator
    sep_style: SeparatorStyle
    sep: str
    sep2: str = None
    # Stop criteria (the default one is EOS token)
    stop_str: str = None
    # Stops generation if meeting any token in this list
    stop_token_ids: List[int] = None

    # Used for the state in the gradio servers.
    # TODO(lmzheng): refactor this
    conv_id: Any = None
    skip_next: bool = False
    model_name: str = None

    def get_prompt(self):
        if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
            ret = self.system + self.sep
            for role, message in self.messages:
                if message:
                    ret += role + ": " + message + self.sep
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
            seps = [self.sep, self.sep2]
            ret = self.system + seps[0]
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += role + ": " + message + seps[i % 2]
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
            ret = self.system
            for role, message in self.messages:
                if message:
                    ret += role + message + self.sep
                else:
                    ret += role
            return ret
        elif self.sep_style == SeparatorStyle.BAIZE:
            ret = self.system + "\n"
            for role, message in self.messages:
                if message:
                    ret += role + message + "\n"
                else:
                    ret += role
            return ret
        elif self.sep_style == SeparatorStyle.DOLLY:
            seps = [self.sep, self.sep2]
            ret = self.system
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += role + ":\n" + message + seps[i % 2]
                    if i % 2 == 1:
                        ret += "\n\n"
                else:
                    ret += role + ":\n"
            return ret
        elif self.sep_style == SeparatorStyle.RWKV:
            ret = self.system
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += (
                        role
                        + ": "
                        + message.replace("\r\n", "\n").replace("\n\n", "\n")
                    )
                    ret += "\n\n"
                else:
                    ret += role + ":"
            return ret
        else:
            raise ValueError(f"Invalid style: {self.sep_style}")

    def append_message(self, role, message):
        self.messages.append([role, message])

    def to_gradio_chatbot(self):
        ret = []
        for i, (role, msg) in enumerate(self.messages[self.offset :]):
            if i % 2 == 0:
                ret.append([msg, None])
            else:
                ret[-1][-1] = msg
        return ret

    def copy(self):
        return Conversation(
            system=self.system,
            roles=self.roles,
            messages=[[x, y] for x, y in self.messages],
            offset=self.offset,
            sep_style=self.sep_style,
            sep=self.sep,
            sep2=self.sep2,
            stop_str=self.stop_str,
            stop_token_ids=self.stop_token_ids,
            conv_id=self.conv_id,
            model_name=self.model_name,
        )

    def dict(self):
        return {
            "system": self.system,
            "roles": self.roles,
            "messages": self.messages,
            "offset": self.offset,
            "conv_id": self.conv_id,
            "model_name": self.model_name,
        }


# A template with one conversation example
conv_one_shot = Conversation(
    system="A chat between a curious human and an artificial intelligence assistant. "
    "The assistant gives helpful, detailed, and polite answers to the human's questions.",
    roles=("Human", "Assistant"),
    messages=(
        (
            "Human",
            "What are the key differences between renewable and non-renewable energy sources?",
        ),
        (
            "Assistant",
            "Renewable energy sources are those that can be replenished naturally in a relatively "
            "short amount of time, such as solar, wind, hydro, geothermal, and biomass. "
            "Non-renewable energy sources, on the other hand, are finite and will eventually be "
            "depleted, such as coal, oil, and natural gas. Here are some key differences between "
            "renewable and non-renewable energy sources:\n"
            "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable "
            "energy sources are finite and will eventually run out.\n"
            "2. Environmental impact: Renewable energy sources have a much lower environmental impact "
            "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, "
            "and other negative effects.\n"
            "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically "
            "have lower operational costs than non-renewable sources.\n"
            "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote "
            "locations than non-renewable sources.\n"
            "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different "
            "situations and needs, while non-renewable sources are more rigid and inflexible.\n"
            "6. Sustainability: Renewable energy sources are more sustainable over the long term, while "
            "non-renewable sources are not, and their depletion can lead to economic and social instability.",
        ),
    ),
    offset=2,
    sep_style=SeparatorStyle.ADD_COLON_SINGLE,
    sep="\n### ",
    stop_str="###",
)


# Vicuna v1.1 template
conv_vicuna_v1_1 = Conversation(
    system="A chat between a curious user and an artificial intelligence assistant. "
    "The assistant gives helpful, detailed, and polite answers to the user's questions.",
    roles=("USER", "ASSISTANT"),
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.ADD_COLON_TWO,
    sep=" ",
    sep2="</s>",
)

# Koala default template
conv_koala_v1 = Conversation(
    system="BEGINNING OF CONVERSATION:",
    roles=("USER", "GPT"),
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.ADD_COLON_TWO,
    sep=" ",
    sep2="</s>",
)

# Dolly V2 default template
conv_dolly = Conversation(
    system="Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n",
    roles=("### Instruction", "### Response"),
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.DOLLY,
    sep="\n\n",
    sep2="### End",
)

# OpenAssistant Pythia default template
conv_oasst = Conversation(
    system="",
    roles=("<|prompter|>", "<|assistant|>"),
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.NO_COLON_SINGLE,
    sep="<|endoftext|>",
)

# StableLM Alpha default template
conv_stablelm = Conversation(
    system="""<|SYSTEM|># StableLM Tuned (Alpha version)
- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
- StableLM will refuse to participate in anything that could harm a human.
""",
    roles=("<|USER|>", "<|ASSISTANT|>"),
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.NO_COLON_SINGLE,
    sep="",
    stop_token_ids=[50278, 50279, 50277, 1, 0],
)

# Baize default template
conv_baize = Conversation(
    system="The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.",
    roles=("[|Human|]", "[|AI|]"),
    messages=(
        ("[|Human|]", "Hello!"),
        ("[|AI|]", "Hi!"),
    ),
    offset=2,
    sep_style=SeparatorStyle.BAIZE,
    sep="[|Human|]",
    stop_str="[|Human|]",
)

# RWKV-4-Raven default template
conv_rwkv = Conversation(
    system="",
    roles=("Bob", "Alice"),
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.RWKV,
    sep="",
    stop_str="\n\n",
)

conv_templates = {
    "baize": conv_baize,
    "conv_one_shot": conv_one_shot,
    "dolly": conv_dolly,
    "koala_v1": conv_koala_v1,
    "oasst": conv_oasst,
    "stablelm": conv_stablelm,
    "vicuna_v1.1": conv_vicuna_v1_1,
    "rwkv": conv_rwkv,
}


def get_default_conv_template(model_name):
    model_name = model_name.lower()
    if "vicuna" in model_name or "output" in model_name:
        return conv_vicuna_v1_1
    elif "koala" in model_name:
        return conv_koala_v1
    elif "dolly-v2" in model_name:
        return conv_dolly
    elif "oasst" in model_name and "pythia" in model_name:
        return conv_oasst
    elif "baize" in model_name:
        return conv_baize
    elif "stablelm" in model_name:
        return conv_stablelm
    elif "rwkv-4" in model_name:
        return conv_rwkv
    return conv_one_shot


if __name__ == "__main__":
    conv = conv_templates["vicuna_v1.1"].copy()
    conv.append_message(conv.roles[0], "Hello!")
    conv.append_message(conv.roles[1], "Hi!")
    conv.append_message(conv.roles[0], "How are you?")
    conv.append_message(conv.roles[1], None)
    print(conv.get_prompt())